65 search results - page 5 / 13 » mt 2006 |
MT
2007
13 years 6 months ago
2007
Statistical machine translation systems are usually trained on large amounts of bilingual text (used to learn a translation model), and also large amounts of monolingual text in th...
MT
2010
13 years 5 months ago
2010
In Minimum Error Rate Training (MERT), BLEU is often used as the error function, despite the fact that it has been shown to have a lower correlation with human judgment than other...
MT
2010
13 years 5 months ago
2010
Recent advances in statistical machine translation have used approximate beam search for NP-complete inference within probabilistic translation models. We present an alternative ap...
MT
2010
13 years 5 months ago
2010
Phrase-based decoding is conceptually simple and straightforward to implement, at the cost of drastically oversimplified reordering models. Syntactically aware models make it pos...
SAC
2006
ACM
14 years 20 days ago
2006
ACM
